Zhengzhong "Jay" Tu

Our group website is live! Check it out here: TACO-Group.

我将于2024年暑假入职得克萨斯农工大学计算机系任助理教授。

招生详情见：招生信息。如有兴趣请填写谷歌 表单；或者将[简历+成绩单+研究兴趣]发给我 tzzhire AT gmail DOT com

I am looking for highly motivated students, in terms of RA/TA/externship/internship/visiting students. Interested candidates are strongly encouraged to contact me by email, with your resume and transcripts. Should you be interested, please fill out the Google forms or email me at: tzzhire AT gmail DOT com

My research interest are broadly focused on multimodal AI, generative AI, autonomous driving, and trustworthy AI:

• Spatial Intelligence: 3DV, gaussian splatting, scene reconstruction, 3D generative models, 3D perception (in autonomous driving)
• Multimodal and Generative AI: Text-to-image generative models, image editing, finetuning, personalization, image restoration, enhancement, video-language models, MLLM, image quality assessment, video quality assessment
• Autonomous Driving: Driving automation, driving scene generation, cooperative autonomous driving, connected and automated vehicles, autonomous driving benchmark, 3DV in driving scenes, end-to-end autonomous driving.
• Trustworthy LLM/VLM: Responsible AI, AI Safety, LLM/VLM robustness, alignment, copyright, jail-breaking, watermarking / fingerprinting
• Machine Learning Systems: Efficient diffusion models/LLM/VLM, model parallelism, model compression, efficient architectures